JP2009545808A5 - - Google Patents

Download PDF

Info

Publication number
JP2009545808A5
JP2009545808A5 JP2009522777A JP2009522777A JP2009545808A5 JP 2009545808 A5 JP2009545808 A5 JP 2009545808A5 JP 2009522777 A JP2009522777 A JP 2009522777A JP 2009522777 A JP2009522777 A JP 2009522777A JP 2009545808 A5 JP2009545808 A5 JP 2009545808A5
Authority
JP
Japan
Prior art keywords
fact
description
search term
factual
word
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
JP2009522777A
Other languages
Japanese (ja)
Other versions
JP5202524B2 (en
JP2009545808A (en
Filing date
Publication date
Priority claimed from US11/496,650 external-priority patent/US7668791B2/en
Application filed filed Critical
Publication of JP2009545808A publication Critical patent/JP2009545808A/en
Publication of JP2009545808A5 publication Critical patent/JP2009545808A5/ja
Application granted granted Critical
Publication of JP5202524B2 publication Critical patent/JP5202524B2/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Claims (20)

電子リソース内で意見と事実との区別をプロセッサにより実施するコンピュータ実装方法であって、  A computer-implemented method for distinguishing opinions and facts within an electronic resource by a processor,
名詞を含む検索用語を受け取ること、  Receiving search terms including nouns,
前記検索用語に一致する関連する電子リソースを発見すること、  Finding relevant electronic resources that match the search term;
前記検索用語に一致する単語を含む前記関連する電子リソースのリスト及び前記リスト内の前記電子リソースの断片を表示すること、  Displaying a list of the associated electronic resources that contain words that match the search term and fragments of the electronic resources in the list;
前記検索用語の名詞と、事実の表現を示唆するように判定された動詞のリストを含むように構成された事実−単語表に一致する1以上の動詞とからなる文書の事実の記述を発見するために、関連する電子リソースをスキャンすること、  Find a factual description of a document consisting of a noun of the search term and a fact-one or more verbs matching the word table configured to include a list of verbs determined to suggest a representation of the fact In order to scan the relevant electronic resources,
前記検索用語と一致しない単語と、前記事実−単語表の単語とからなる事実の抽出処理から、前記関連する電子リソースの部分を削除すること、  Deleting the relevant electronic resource part from the fact extraction process consisting of the word that does not match the search term and the fact-word table word;
前記関連する電子リソースの部分を削除することの後に、前記事実の記述の言語成分を識別するために、前記発見した事実の記述を調査すること、  Examining the found factual description to identify a linguistic component of the factual description after deleting the portion of the associated electronic resource;
前記識別した言語成分に基づいた事実として事実の記述を提示するか否かを決定すること、  Determining whether to present a factual description as a fact based on the identified linguistic component;
前記検索用語と、前記検索用語に関連する事実であると判定された事実の記述とを含む文書の少なくとも一部を表現すること  Expressing at least a part of a document including the search term and a description of the fact determined to be a fact related to the search term
から成ることを特徴とする方法。  A method characterized by comprising.
前記識別した言語成分に基づいた事実として事実の記述を提示するか否かを決定することは、
ある事実の記述を考慮からはずすために、前記事実の記述の前記言語成分に関する除外規則を適用すること、
前記事実の記述にスコアをつけること、
考慮するために残っている事実の記述の各々の前記スコアを閾値と比較すること、
前記閾値を超えるスコアを有する事実の記述の各々に対して、事実として前記事実の記述を含む文章の少なくとも一部を提示すること
から成ることを特徴とする請求項1に記載の方法。
Determining whether to present a factual description as a fact based on the identified linguistic component;
Applying an exclusion rule for the linguistic component of the factual description in order to remove the factual description from consideration;
Scoring the statement of facts;
Comparing the score of each of the remaining factual descriptions to consider with a threshold;
2. The method of claim 1, comprising presenting at least a portion of a sentence containing the fact description as a fact for each fact description having a score that exceeds the threshold.
更に会話の部分と共に前記事実の記載の単語にタグを付けることから成ることを特徴とする請求項2に記載の方法。   3. The method of claim 2, further comprising tagging said factual word along with the conversation portion. 会話の部分と共に前記事実の記載の単語にタグを付けることは、単語が動詞か名詞のいずれかであるとき、名詞タグを適用することから成ることを特徴とする請求項3に記載の方法。   4. The method of claim 3, wherein tagging the factual word along with the conversation portion comprises applying a noun tag when the word is either a verb or a noun. 前記除外規則を適用することは、主語の役目を有する統語上の句のための規則の第1のセットを適用することと、目的語の役目を有する統語上の句のための規則の第2のセットを適用することから成ることを特徴とする請求項4に記載の方法。   Applying the exclusion rule applies a first set of rules for a syntactic phrase having a subject role and applying a second set of rules for a syntactic phrase having a subject role 5. The method of claim 4, comprising: 規則の前記第1のセットを適用することは、主語又は目的語の意見又は偏った修飾語句を有する名詞句を除外することから成ることを特徴とする請求項5に記載の方法。   6. The method of claim 5, wherein applying the first set of rules comprises excluding noun phrases that have subject or object opinions or biased modifier phrases. 規則の前記第2のセットを適用することは、
固有名詞でない限定記述を含む主語名詞句を除外すること、
代名詞を含む名詞句を除外すること、文書の冒頭に現れない主語名詞句を除外することから成ることを特徴とする請求項5に記載の方法。
Applying said second set of rules is
Excluding subject noun phrases that contain qualifying statements that are not proper nouns;
6. The method of claim 5, comprising excluding noun phrases that include pronouns and excluding subject noun phrases that do not appear at the beginning of the document.
前記名詞句の役目に関係なく、更に規則の第3のセットを適用することから成ることを特徴とする請求項5に記載の方法。   6. The method of claim 5, further comprising applying a third set of rules regardless of the role of the noun phrase. 規則の前記第3のセットを適用することは、前記文章の句読点が疑問符である事実の記述を除外することと、ストップワードを含む句を有する文章を除外することから成ることを特徴とする請求項8に記載の方法。   Applying the third set of rules comprises excluding a statement of fact that the punctuation of the sentence is a question mark and excluding a sentence having a phrase that includes a stop word. Item 9. The method according to Item 8. 前記事実の記述にスコアを付けることは、前記除外規則の適用後、又は適用中のどちらかに考慮するために残っているこれらの事実の記述だけにスコアを付けることから成ることを特徴とする請求項2に記載の方法。   Scoring the description of facts consists of scoring only those factual descriptions that remain to be considered either after application of the exclusion rule or during application. The method of claim 2. コンピュータが読みとり可能な記録媒体であって、  A computer-readable recording medium,
名詞を含む検索用語を受け取ること、  Receiving search terms including nouns,
前記検索用語に一致する関連する電子リソースを発見すること、  Finding relevant electronic resources that match the search term;
前記検索用語に一致する単語を含む前記関連する電子リソースのリスト及び前記リスト内の前記電子リソースの断片を表示すること、  Displaying a list of the associated electronic resources that contain words that match the search term and fragments of the electronic resources in the list;
前記検索用語の名詞と、事実の表現を示唆するように判定された動詞のリストを含むように構成された事実−単語表の単語に一致する1以上の動詞とからなる文書の事実の記述を発見するために、複数の関連する電子文書を構文解析すること、  A factual description of a document consisting of the search term noun and a fact-one or more verbs that match a word in the word table configured to include a list of verbs determined to suggest a representation of the fact Parsing multiple related electronic documents to discover,
前記検索用語と一致しない単語と、前記事実−単語表の単語とからなる事実の抽出処理から、前記関連する電子文書の部分を削除すること、  Deleting a portion of the related electronic document from a fact extraction process consisting of a word that does not match the search term and a fact-word table word;
前記関連する電子文書の部分を削除することの後に、前記事実の記述の言語成分を識別するために、前記発見した事実の記述を調査すること、  Examining the found factual description to identify a linguistic component of the factual description after deleting the relevant electronic document portion;
前記言語成分に関する候補となる事実の記述に除外規則を適用することにより、前記識別した言語成分に基づいた前記検索用語に関連する事実として事実の記述を提示するか否かを決定すること、  Determining whether to present a description of the fact as a fact related to the search term based on the identified language component by applying an exclusion rule to the description of the candidate fact about the language component;
一致する事実−単語表に基づき、かつ、主語と目的語の個々の重みに基づき、候補となる事実の記述をスコアリングすること、  Matching facts-scoring candidate factual descriptions based on the word table and based on the individual weights of the subject and object,
前記除外規則および事実の記述のスコアリングに従って、前記候補となる事実の記述を考慮からはずすこと、  Removing the candidate fact description from consideration according to the exclusion rule and fact scoring;
前記検索用語と、前記検索用語に関連する事実であると判定された事実の記述とを含む文書の少なくとも一部を表現すること  Expressing at least a part of a document including the search term and a description of the fact determined to be a fact related to the search term
から成ることを特徴とする行為を、プロセッサにより実行されたときに、プロセッサに実行させる実効可能プログラム命令を含むコンピュータが読みとり可能な記録媒体。  A computer-readable recording medium containing executable program instructions that cause a processor to execute an action characterized by comprising the following:
前記行為は、さらに電子文書の集合を検索して、前記検索用語を含むこれらの文書を発見することにより前記複数の文書を得ることから成り、
前記集合は、前記複数の電子文書を解析する前に前記検索用語を含むこれらの文書を発見するために検索されること
を特徴とする請求項11に記載のコンピュータが読みとり可能な記録媒体。
The act further comprises retrieving the plurality of documents by searching a collection of electronic documents and finding those documents that include the search term;
The computer-readable recording medium of claim 11, wherein the set is searched to find those documents that include the search term before analyzing the plurality of electronic documents.
前記行為は、さらに前記電子文書を入手して前記検索用語を受け取る前に事実の記述を提示すること、又前記電子文書と事実の記述を検索して、これらの電子文書と前記検索用語に関連する対応する事実の記述を見つけることから成ることを特徴とする請求項11に記載のコンピュータが読取り可能な記録媒体。   The act further presents a description of the facts prior to obtaining the electronic document and receiving the search term, or searching the electronic document and fact description and relating to the electronic document and the search term. The computer-readable medium of claim 11, comprising finding a corresponding factual description. 前記行為は、さらに考慮するために残っている事実の記述の各々の前記スコアを閾値に対して比較すること、
前記検索用語を含み、前記閾値を超えるスコアを有する電子文書から取られた事実の記述の各々に対して、前記検索用語に関連する事実として前記事実の記述を含む前記文章の少なくとも一部を提示することから成ることを特徴とする請求項11に記載のコンピュータが読みとり可能な記録媒体。
The act of comparing the score of each of the remaining factual descriptions for further consideration against a threshold;
For each factual description taken from an electronic document that includes the search term and has a score above the threshold, present at least a portion of the sentence that includes the factual description as a fact associated with the search term The computer-readable recording medium according to claim 11, comprising:
前記事実の記述にスコアを付けることは、前記除外規則を適用した後に考慮するために残っているこれらの事実の記述にだけスコアをつけること
から成ることを特徴とする請求項14に記載のコンピュータが読みとり可能な記録媒体。
15. The computer of claim 14, wherein scoring the description of facts comprises scoring only those factual descriptions that remain to be considered after applying the exclusion rule. Is a readable recording medium.
本文情報から成る複数の電子リソースを含むストレージと、  Storage containing multiple electronic resources consisting of body information,
プロセッサとから成るコンピュータシステムであって、  A computer system comprising a processor,
前記プロセッサは、名詞を含む検索用語を受け取り、前記検索用語と一致する関連する電子リソースを発見し、前記検索用語に一致する単語を含む前記関連する電子リソースのリスト及び前記リスト内の前記電子リソースの断片を表示し、電子文書のセットから前記検索用語に関する事実を提示するための要求を受け取り、前記検索用語の名詞と、事実の表現を示唆するように判定された動詞のリストを含むように構成された事実−単語表の単語に一致する1以上の動詞とからなる文書の事実の記述を発見するために、前記関連する電子文書を構文解析し、前記検索用語と一致しない単語と、前記事実−単語表の単語とからなる事実の抽出処理から、前記関連する電子文書の部分を削除し、前記関連する電子文書の部分を削除した後に、前記事実の記述の言語成分を識別するために、前記発見した事実の記述を調査し、前記識別した言語成分に基づいた事実として事実の記述を提示するか否かを決定し、前記事実として提示されると判定された事実の記述と、前記検索用語に関連する事実の記述とを含む文書の少なくとも一部を表現する  The processor receives a search term that includes a noun, finds an associated electronic resource that matches the search term, and includes a list of the associated electronic resource that includes a word that matches the search term and the electronic resource in the list To receive a request to present facts about the search term from a set of electronic documents and to include a noun of the search term and a list of verbs determined to suggest a representation of the fact In order to find a factual description of a document consisting of one or more verbs that match words in a structured fact-word table, the related electronic document is parsed, and the words that do not match the search term; After deleting the related electronic document part from the fact extraction process including facts and words in the word table, and deleting the related electronic document part, In order to identify the linguistic component of the actual description, the description of the found fact is examined, it is determined whether or not the fact description is presented as a fact based on the identified linguistic component, and is presented as the fact. Represent at least a portion of a document including a description of the fact determined to be and a description of the fact associated with the search term
ことを特徴とするコンピュータシステム。  A computer system characterized by that.
表示装置を更に備え、前記表示装置上に前記文章の少なくとも前記部分を表示することにより、前記プロセッサが前記文章の少なくとも前記部分を提示することを特徴とする請求項16に記載のコンピュータシステム。   17. The computer system of claim 16, further comprising a display device, wherein the processor presents at least the portion of the sentence by displaying at least the portion of the sentence on the display device. ネットワークインタフェースを更に備え、前記ネットワークインタフェースを介してこれらの部分を他のコンピュータに出力することにより、前記プロセッサが前記文章の少なくとも前記部分を提示することを特徴とする請求項16に記載のコンピュータシステム。   The computer system of claim 16, further comprising a network interface, wherein the processor presents at least the portion of the sentence by outputting the portion to another computer via the network interface. . ネットワークインタフェースを更に備え、前記ストレージは前記ネットワークインタフェースを介して前記プロセッサによりアクセス可能なことを特徴とする請求項16に記載のコンピュータシステム。   The computer system of claim 16, further comprising a network interface, wherein the storage is accessible by the processor via the network interface. 前記事実の記述の前記言語成分に関連して除外規則を適用して前記事実の記述の一部を考慮から外すこと、
前記事実の記述にスコアを付けること、
閾値に対して考慮するために残存する事実の記述の各々のスコアを比較すること、
前記検索用語を含み、前記閾値を超えるスコアを有する事実の記述の各々に対して、前記検索用語に関連する事実として前記事実の記述を含む前記文章の少なくとも前記部分を提示すること、
により、事実として事実の記述を提示するか否かを前記プロセッサが決定することを特徴とする請求項16に記載のコンピュータシステム。
Applying an exclusion rule in relation to the linguistic component of the factual description to exclude a part of the factual description from consideration;
Scoring the statement of facts;
Comparing the scores of each of the remaining factual descriptions to consider against the threshold;
Presenting at least the portion of the sentence that includes the fact description as a fact associated with the search term for each description of the fact that includes the search term and has a score that exceeds the threshold;
17. The computer system of claim 16, wherein the processor determines whether to present a factual description as a fact.
JP2009522777A 2006-07-31 2007-07-20 Optimizing fact extraction using a multi-stage approach Active JP5202524B2 (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US11/496,650 US7668791B2 (en) 2006-07-31 2006-07-31 Distinguishing facts from opinions using a multi-stage approach
US11/496,650 2006-07-31
PCT/US2007/016435 WO2008016491A1 (en) 2006-07-31 2007-07-20 Optimization of fact extraction using a multi-stage approach

Publications (3)

Publication Number Publication Date
JP2009545808A JP2009545808A (en) 2009-12-24
JP2009545808A5 true JP2009545808A5 (en) 2010-09-09
JP5202524B2 JP5202524B2 (en) 2013-06-05

Family

ID=38987573

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2009522777A Active JP5202524B2 (en) 2006-07-31 2007-07-20 Optimizing fact extraction using a multi-stage approach

Country Status (10)

Country Link
US (1) US7668791B2 (en)
EP (1) EP2050019A4 (en)
JP (1) JP5202524B2 (en)
AU (1) AU2007281638B2 (en)
BR (1) BRPI0714311A2 (en)
MX (1) MX2009000588A (en)
NO (1) NO20085387L (en)
RU (1) RU2451999C2 (en)
TW (1) TWI431493B (en)
WO (1) WO2008016491A1 (en)

Families Citing this family (54)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7269875B1 (en) * 2003-11-19 2007-09-18 David Brian Grimes Cleaning apparatus
US9495358B2 (en) 2006-10-10 2016-11-15 Abbyy Infopoisk Llc Cross-language text clustering
US8671341B1 (en) * 2007-01-05 2014-03-11 Linguastat, Inc. Systems and methods for identifying claims associated with electronic text
US8190628B1 (en) * 2007-11-30 2012-05-29 Google Inc. Phrase generation
EP2294519A1 (en) 2008-06-13 2011-03-16 Neil Young A sortable and updateable data compilation and archiving platform and uses thereof
US20110231387A1 (en) * 2010-03-22 2011-09-22 Yahoo! Inc. Engaging content provision
US8719692B2 (en) 2011-03-11 2014-05-06 Microsoft Corporation Validation, rejection, and modification of automatically generated document annotations
US8812301B2 (en) * 2011-09-26 2014-08-19 Xerox Corporation Linguistically-adapted structural query annotation
CN102929934A (en) * 2012-09-25 2013-02-13 东莞宇龙通信科技有限公司 Photograph information display method and mobile terminal
US10922326B2 (en) * 2012-11-27 2021-02-16 Google Llc Triggering knowledge panels
US10289653B2 (en) 2013-03-15 2019-05-14 International Business Machines Corporation Adapting tabular data for narration
USD805535S1 (en) 2013-06-04 2017-12-19 Abbyy Production Llc Display screen or portion thereof with a transitional graphical user interface
USD802609S1 (en) 2013-06-04 2017-11-14 Abbyy Production Llc Display screen with graphical user interface
US9164977B2 (en) 2013-06-24 2015-10-20 International Business Machines Corporation Error correction in tables using discovered functional dependencies
US9600461B2 (en) 2013-07-01 2017-03-21 International Business Machines Corporation Discovering relationships in tabular data
US9830314B2 (en) 2013-11-18 2017-11-28 International Business Machines Corporation Error correction in tables using a question and answer system
RU2665239C2 (en) 2014-01-15 2018-08-28 Общество с ограниченной ответственностью "Аби Продакшн" Named entities from the text automatic extraction
RU2586577C2 (en) 2014-01-15 2016-06-10 Общество с ограниченной ответственностью "Аби ИнфоПоиск" Filtering arcs parser graph
US10331782B2 (en) 2014-11-19 2019-06-25 Lexisnexis, A Division Of Reed Elsevier Inc. Systems and methods for automatic identification of potential material facts in documents
US9626358B2 (en) 2014-11-26 2017-04-18 Abbyy Infopoisk Llc Creating ontologies by analyzing natural language texts
RU2592396C1 (en) 2015-02-03 2016-07-20 Общество с ограниченной ответственностью "Аби ИнфоПоиск" Method and system for machine extraction and interpretation of text information
RU2610241C2 (en) 2015-03-19 2017-02-08 Общество с ограниченной ответственностью "Аби ИнфоПоиск" Method and system for text synthesis based on information extracted as rdf-graph using templates
US10095740B2 (en) * 2015-08-25 2018-10-09 International Business Machines Corporation Selective fact generation from table data in a cognitive system
CN105260091B (en) * 2015-09-07 2019-06-21 努比亚技术有限公司 Photo processing method and device
US10776587B2 (en) * 2016-07-11 2020-09-15 International Business Machines Corporation Claim generation
RU2637992C1 (en) * 2016-08-25 2017-12-08 Общество с ограниченной ответственностью "Аби Продакшн" Method of extracting facts from texts on natural language
CN106648390B (en) * 2016-12-05 2018-12-21 网易(杭州)网络有限公司 A kind of control instruction generation method, device and mobile terminal
CN106649786B (en) * 2016-12-28 2020-04-07 北京百度网讯科技有限公司 Answer retrieval method and device based on deep question answering
CN106924963B (en) * 2017-04-26 2023-06-27 温州大学 Entertainment targeting machine for vision and hearing rehabilitation training
CN108038263A (en) * 2017-11-15 2018-05-15 南京邮电大学 Consider the uncertain chip multiple parameters yield prediction method of performance dependency structure
CN108257380B (en) * 2017-12-05 2020-11-10 北京掌行通信息技术有限公司 Method and system for detecting congestion event based on road condition information
US10303771B1 (en) * 2018-02-14 2019-05-28 Capital One Services, Llc Utilizing machine learning models to identify insights in a document
CN109344993B (en) * 2018-08-23 2021-08-24 江西省水利科学研究院 River channel flood peak water level forecasting method based on conditional probability distribution
CN111026597B (en) * 2019-01-31 2023-12-26 安天科技集团股份有限公司 Detection method and device for hidden storage space of chip and storage medium
CN110007589B (en) * 2019-02-26 2021-05-18 湖南盛世威得科技有限公司 Intelligent watch with automatic fire distress function
CN110057634B (en) * 2019-04-11 2021-09-07 东北石油大学 Device and method for manufacturing core cracks
CN111858225A (en) * 2019-04-28 2020-10-30 中国移动通信集团上海有限公司 Delay prediction method, device, equipment and computer storage medium
CN111090785A (en) * 2019-06-10 2020-05-01 工盒(嘉兴)网络技术有限公司 Fastening cloud system
CN110597108B (en) * 2019-08-23 2021-12-21 广州电力设计院有限公司 Cable tunnel area control system, control method and device and computer equipment
CN110737010B (en) * 2019-09-19 2021-11-16 西安空间无线电技术研究所 Safe positioning time service signal generation system based on low-earth-orbit communication satellite
CN111078849B (en) * 2019-12-02 2023-07-25 百度在线网络技术(北京)有限公司 Method and device for outputting information
CN111126057B (en) * 2019-12-09 2023-08-01 航天科工网络信息发展有限公司 Case scenario accurate sentencing system of hierarchical neural network
DE102020103941A1 (en) * 2020-02-14 2021-08-19 Grimme Landmaschinenfabrik Gmbh & Co. Kg Method for operating a machine for harvesting and / or separating root crops, associated machine and associated computer program product
JP2021164005A (en) * 2020-03-30 2021-10-11 Kddi株式会社 Image decoding device, image decoding method, and program
CN111526397A (en) * 2020-03-30 2020-08-11 深圳市懿美莱科技有限公司 Intelligent home network player
CN111836065B (en) * 2020-07-14 2022-04-29 北京场景互娱传媒科技有限公司 Intelligent method for automatically hiding live broadcast trademark
CN111882828B (en) * 2020-07-22 2021-08-20 淮北智淮科技有限公司 Landslide prevention early warning device and using method thereof
CN112182895B (en) * 2020-10-10 2022-08-23 中际联合(天津)科技有限公司 Automatic analysis method for arrangement scheme diagram of wind turbine tower ladder and anti-falling
CN112890771B (en) * 2021-01-14 2022-08-26 四川写正智能科技有限公司 Child watch capable of monitoring sleep state based on millimeter wave radar sensor
US11687539B2 (en) 2021-03-17 2023-06-27 International Business Machines Corporation Automatic neutral point of view content generation
US11972210B2 (en) * 2021-05-13 2024-04-30 Motorola Solutions, Inc. System and method for predicting a penal code and modifying an annotation based on the prediction
CN115191786B (en) * 2022-08-04 2023-12-19 慕思健康睡眠股份有限公司 Control method, device, equipment and storage medium
CN115432851B (en) * 2022-08-23 2023-06-23 长兴瑷晟环保装备有限公司 High-efficient coagulation hydrodynamic cavitation all-in-one
CN118278385B (en) * 2024-05-29 2024-09-17 暗物智能科技(广州)有限公司 Test method and device based on chapter rolling surface analysis and readable storage medium

Family Cites Families (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0756933A (en) * 1993-06-24 1995-03-03 Xerox Corp Method for retrieval of document
US5519608A (en) * 1993-06-24 1996-05-21 Xerox Corporation Method for extracting from a text corpus answers to questions stated in natural language by using linguistic analysis and hypothesis generation
US5331556A (en) * 1993-06-28 1994-07-19 General Electric Company Method for natural language data processing using morphological and part-of-speech information
US5715468A (en) * 1994-09-30 1998-02-03 Budzinski; Robert Lucius Memory system for storing and retrieving experience and knowledge with natural language
JP2000029902A (en) * 1998-07-15 2000-01-28 Nec Corp Structure document classifying device and recording medium where program actualizing same structured document classifying device by computer is recorded, and structured document retrieval system and recording medium where program actualizing same structured document retrieval system by computer is recorded
US6167370A (en) * 1998-09-09 2000-12-26 Invention Machine Corporation Document semantic analysis/selection with knowledge creativity capability utilizing subject-action-object (SAO) structures
US6741986B2 (en) * 2000-12-08 2004-05-25 Ingenuity Systems, Inc. Method and system for performing information extraction and quality control for a knowledgebase
US6665661B1 (en) * 2000-09-29 2003-12-16 Battelle Memorial Institute System and method for use in text analysis of documents and records
JP4630480B2 (en) * 2001-03-19 2011-02-09 株式会社東芝 Summary extraction program, document analysis support program, summary extraction method, document analysis support method, document analysis support system
JP2001357064A (en) * 2001-04-09 2001-12-26 Toshiba Corp Information sharing support system
US9009590B2 (en) * 2001-07-31 2015-04-14 Invention Machines Corporation Semantic processor for recognition of cause-effect relations in natural language documents
US7526425B2 (en) * 2001-08-14 2009-04-28 Evri Inc. Method and system for extending keyword searching to syntactically and semantically annotated data
US7254530B2 (en) * 2001-09-26 2007-08-07 The Trustees Of Columbia University In The City Of New York System and method of generating dictionary entries
US7426509B2 (en) * 2002-11-15 2008-09-16 Justsystems Evans Research, Inc. Method and apparatus for document filtering using ensemble filters
WO2004072780A2 (en) * 2003-02-05 2004-08-26 Verint Systems, Inc. Method for automatic and semi-automatic classification and clustering of non-deterministic texts
RU2236699C1 (en) * 2003-02-25 2004-09-20 Открытое акционерное общество "Телепортал. Ру" Method for searching and selecting information with increased relevance
KR100515641B1 (en) * 2003-04-24 2005-09-22 우순조 Method for sentence structure analysis based on mobile configuration concept and method for natural language search using of it
US20050108630A1 (en) * 2003-11-19 2005-05-19 Wasson Mark D. Extraction of facts from text
US7496500B2 (en) * 2004-03-01 2009-02-24 Microsoft Corporation Systems and methods that determine intent of data and respond to the data based on the intent
US7970600B2 (en) * 2004-11-03 2011-06-28 Microsoft Corporation Using a first natural language parser to train a second parser
US20070027860A1 (en) * 2005-07-28 2007-02-01 International Business Machines Corporation Method and apparatus for eliminating partitions of a database table from a join query using implicit limitations on a partition key value
US7376551B2 (en) * 2005-08-01 2008-05-20 Microsoft Corporation Definition extraction

Similar Documents

Publication Publication Date Title
JP2009545808A5 (en)
KR102256240B1 (en) Non-factoid question-and-answer system and method
US9569527B2 (en) Machine translation for query expansion
JP5825676B2 (en) Non-factoid question answering system and computer program
TWI431493B (en) Method, computer readable storage medium, and computer system for optimization of fact extraction using a multi-stage approach
KR101508070B1 (en) Method for word sense diambiguration of polysemy predicates using UWordMap
Gupta et al. Automatic keywords extraction for Punjabi language
Sardinha An assessment of metaphor retrieval methods
JP5718405B2 (en) Utterance selection apparatus, method and program, dialogue apparatus and method
CN112036120A (en) Skill phrase extraction method
US8108391B1 (en) Identifying non-compositional compounds
Chaibi et al. Topic segmentation for textual document written in arabic language
JP6106489B2 (en) Semantic analyzer and program
Ehsan et al. A Pairwise Document Analysis Approach for Monolingual Plagiarism Detection.
US10572592B2 (en) Method, device, and computer program for providing a definition or a translation of a word belonging to a sentence as a function of neighbouring words and of databases
JP4934115B2 (en) Keyword extraction apparatus, method and program
JP2008257511A (en) Technical term extraction device, method, and program
Elghannam et al. Keyphrase based evaluation of automatic text summarization
Ram et al. Identification of plagiarism using syntactic and semantic filters
Généreux et al. Towards a validated model for affective classification of texts
Xu et al. A machine learning approach to recognizing acronyms and their expansion
Kliegr et al. Wikipedia as the premiere source for targeted hypernym discovery
Kokkinakis et al. Investigating the Effects of MWE Identification in Structural Topic Modelling
Pinheiro et al. Knowledge-intensive word disambiguation via common-sense and wikipedia
Vechtomova Related Entity Finding: University of Waterloo at TREC 2010 Entity Track.